Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    舯
    -0.07
    (Runtime
    -0.07
    |.↵
    -0.07
     Bowl
    -0.07
     kommun
    -0.07
    SCRIBE
    -0.07
     ny
    -0.07
     którą
    -0.07
    ГО
    -0.07
    Patch
    -0.07
    POSITIVE LOGITS
     lãi
    0.07
    続け
    0.07
    тверд
    0.07
    겠다
    0.07
     overl
    0.06
     expressed
    0.06
     그렇
    0.06
     frivol
    0.06
     reservations
    0.06
     "*
    0.06
    Act Density 0.007%

    No Known Activations